GPU comparison
AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) vs NVIDIA RTX 5080 (16GB) for local LLMs
How the two stack up for running open-source LLMs locally — memory, bandwidth, price, and how many of the 34 tracked models each one can run.
| AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) | NVIDIA RTX 5080 (16GB) | |
|---|---|---|
| Memory | 128.0 GB | 16.0 GB |
| Bandwidth | 256 GB/s | 960 GB/s |
| Price (approx) | $2,999 | $1,399 |
| LLMs it runs | 30 of 34 | 18 of 34 |
| Best model it runs | Gemma 4 31B · 10–15 tok/s | Gemma 4 26B-A4B (MoE) · 167–251 tok/s |
The AMD Ryzen AI Max+ 395 “Strix Halo” (128GB) runs 12 more of the tracked models (30 vs 18), thanks to its 128.0 GB of memory. The NVIDIA RTX 5080 (16GB) has more memory bandwidth (960 GB/s), so it generates tokens faster at the same model and quant.